library(tidyverse)
library(flextable)
library(here)
library(readxl)
library(modelsummary)
library(janitor)
library(performance)
library(ggplot2)

# Demographic
age <- read_csv(here("data", "TAG_age_session_dates_4waves.csv"))
age <- clean_names(age)

race <- read_excel(here("data", "TAG_W1_Race_Ethnicity.xlsx"))
race <- clean_names(race)

# Emotion Regulation(ERQ)
erq <- read_csv(here("data", "ERQ_Wave1.csv"))
erq <- erq %>% 
       clean_names() %>% 
       distinct(tagid, .keep_all = TRUE)

# Adolescent Depression(CESDC)
cesdc <- read_csv(here("data", "CESDC_Wave1.csv"))
cesdc <- clean_names(cesdc)

race_clean <- race %>%
  mutate(
    w1_ethnicity = as.character(w1_ethnicity),
    w1_ethnicity = if_else(
      str_detect(w1_ethnicity, ","),
      "g. Multi-racial",
      w1_ethnicity
    )
  )

age <- age %>% 
  mutate(W1_mean_age = (w1s1_age + w1s2_age)/2) 

# Check mean age for sample
age_summary <- age %>%
  summarize(
    mean_W1_age = mean(W1_mean_age, na.rm = TRUE),
    sd_W1_age   = sd(W1_mean_age, na.rm = TRUE),
  )
print(age_summary)

df <- erq %>% 
  left_join(cesdc, by= 'tagid')

df <- df %>% 
     left_join(age, by = 'tagid')

df <- df %>% 
     left_join(race_clean, by = 'tagid') %>% 
     select(tagid, erq_reappraisal_total, erq_suppression_total, ces_dc_total_75perc, W1_mean_age, w1_ethnicity, 
            w1s1_date, w1s1_age, w1s2_date, w1s2_age, w2s1_date, w2s1_age, w2s2_date, w2s2_age, 
            w3s1_date, w3s1_age, w3s2_date, w3s2_age, w4s1_date, w4s1_age, w4s2_date, w4s2_age
            )

df <- df %>%
  rename(
    wave1_session1_date = w1s1_date,
    wave1_session1_age  = w1s1_age,
    wave1_session2_date = w1s2_date,
    wave1_session2_age  = w1s2_age,

    wave2_session1_date = w2s1_date,
    wave2_session1_age  = w2s1_age,
    wave2_session2_date = w2s2_date,
    wave2_session2_age  = w2s2_age,

    wave3_session1_date = w3s1_date,
    wave3_session1_age  = w3s1_age,
    wave3_session2_date = w3s2_date,
    wave3_session2_age  = w3s2_age,

    wave4_session1_date = w4s1_date,
    wave4_session1_age  = w4s1_age,
    wave4_session2_date = w4s2_date,
    wave4_session2_age  = w4s2_age
  )

# Tidy
df2 <- df %>%
  mutate(across(starts_with("wave"), as.character))

df_long <- df2 %>%
  pivot_longer(
    cols = starts_with("wave"),
    names_to = c("wave", "session", "info"),
    names_sep = "_",
    values_to = "value"
  ) %>%
  mutate(
    wave    = parse_number(wave),
    session = parse_number(session)
  )

df_tidy <- df_long %>%
  pivot_wider(
    names_from = info,
    values_from = value
  )

# Filter
df_final <- df_tidy %>% 
  filter(wave == 1, session == 1)

ggplot(df_tidy, aes(x = age, y = tagid)) +
  geom_line(aes(group = tagid), size = .5, alpha = .4) +
  geom_point(aes(color = as.factor(wave)), size = 2) +
  labs(
    x = "Age",
    y = "TAG Participant",
    title = "Age by Wave",
    color = "Wave"
  ) +
  theme_classic() +
  theme(
    legend.position = "top",
    axis.text.y = element_blank(),
    axis.ticks.y = element_blank()
  )

df_names <- df_tidy %>% 
    select(-wave, -session) %>% 
    rename(
    Reappraisal       = erq_reappraisal_total,
    Suppression       = erq_suppression_total,
    Depression        = ces_dc_total_75perc,
    Age               = W1_mean_age,
    Ethnicity         = w1_ethnicity
    )

datasummary_skim(df_names,
                 title = "Table 1. Sample Descriptive Statistics")

rq1 <- lm(df_tidy$ces_dc_total_75perc ~ df_tidy$erq_reappraisal_total)
check_model(rq1)

rq2 <- lm(df_tidy$ces_dc_total_75perc ~ df_tidy$erq_suppression_total)
check_model(rq2)

ex1 <- lm(df_tidy$ces_dc_total_75perc ~ df_tidy$erq_suppression_total + df_tidy$erq_reappraisal_total)
check_model(ex1)

ex2 <- lm(df_tidy$ces_dc_total_75perc ~ df_tidy$erq_reappraisal_total * df_tidy$W1_mean_age)
check_model(ex2)

ex3 <- lm(df_tidy$ces_dc_total_75perc ~ df_tidy$erq_suppression_total * df_tidy$W1_mean_age)
check_model(ex3)

modelsummary(
  list(
    "Reappraisal" = rq1,
    "Suppression" = rq2),
  coef_map = c(
    "(Intercept)"                     = "Intercept",
    "df_tidy$erq_reappraisal_total"   = "Reappraisal (ERQ)",
    "df_tidy$erq_suppression_total"   = "Suppression (ERQ)"
  ),
  stars = TRUE,
  title = "Table 2. Model Summary for RQ1 and RQ2"
  )

modelsummary(
  list(
    "Suppression + Reappraisal" = ex1,
    "Reappraisal × Age Interaction" = ex2,
    "Suppression × Age Interaction" = ex3),
    coef_map = c(
    "(Intercept)"                     = "Intercept",
    "df_tidy$erq_reappraisal_total"   = "Reappraisal (ERQ)",
    "df_tidy$erq_suppression_total"   = "Suppression (ERQ)",
    "df_tidy$erq_reappraisal_total:df_tidy$W1_mean_age" = "Reappraisal x Age",
    "df_tidy$erq_suppression_total:df_tidy$W1_mean_age" = "Suppression x Age"),
  stars = TRUE,
  title = "Table 3. Model Summaries for Multiple Regression and Interaction Models"
  )

ggplot(df_tidy, aes(x=erq_reappraisal_total, y=ces_dc_total_75perc))+
  geom_point(color="Dodgerblue3")+
  geom_smooth(method = lm, color="Aquamarine3")+
  labs(x="Reappraisal", y="Depression")

ggplot(df_tidy,aes(x=erq_suppression_total, y=ces_dc_total_75perc))+
  geom_point(color="Dodgerblue3")+
  geom_smooth(method = lm, color="Aquamarine3")+
  labs(x="Suppression", y="Depression")